{"id":"2610.13672","title":"Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction","url":"https://codeofpaper.com/paper/2610.13672","arxiv_url":"https://arxiv.org/abs/2610.13672","published":"2026-10-09","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}